chaos-experiment

chaos-experiment is a skill for Claude Code, Codex from harness/harness-skills. It costs 120 tokens per session (1,432 once invoked), scanned A, original, Apache-2.0.

A tool for running chaos experiments, which deliberately create failures such as deleted containers, high CPU use, or network problems. It uses Harness Chaos Engineering to test how systems respond.

In plain words
What is it for?
Use it to test resilience by simulating container deletion, CPU stress, or network faults, then checking the experiment runs.
Why use it?
It helps reveal reliability weaknesses before an unexpected outage does. Teams can inspect available infrastructure, create experiments, run them, and monitor the results.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to test resilience by simulating container deletion, CPU stress, or network faults, then checking the experiment runs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/harness/harness-skills/chaos-experiment
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add harness/harness-skills --skill chaos-experiment
Clone the repo
git clone --depth 1 https://github.com/harness/harness-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for chaos-experiment

README.md
[![agentmods](https://agentmods.dev/badge/skills/harness/harness-skills/chaos-experiment/github.svg)](https://agentmods.dev/skills/harness/harness-skills/chaos-experiment)
Your own site
<a href="https://agentmods.dev/skills/harness/harness-skills/chaos-experiment"><img src="https://agentmods.dev/badge/skills/harness/harness-skills/chaos-experiment/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for chaos-experiment

Your own site · 80×15
<a href="https://agentmods.dev/skills/harness/harness-skills/chaos-experiment"><img src="https://agentmods.dev/badge/skills/harness/harness-skills/chaos-experiment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 120 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,432 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00120 $0.01432
Opus 5 $0.00060 $0.00716
Sonnet 5 $0.00024 $0.00286
Haiku 4.5 $0.00012 $0.00143

Measured yesterday against content hash ad9f86669304, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

chaos-experiment scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/chaos-experiment/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Chaos Experiment

Create, edit, and answer reference questions about Harness Chaos Experiments — faults, probes, actions, and the underlying ChaosExperiment manifest — via MCP.

MANDATORY — Tool Result Verification:

  • NEVER claim a tool call succeeded without an explicit success response from the tool.
  • NEVER fabricate, assume, or pre-empt tool results. If you called a tool and did not receive a confirmed result, say so and retry.
  • When a tool returns a review/elicitation prompt (e.g., "Waiting for user to review before update..."), the user's approval does NOT mean the operation completed. You MUST wait for the follow-up tool response confirming execution before reporting success.
  • If the tool response is ambiguous or missing, tell the user honestly and offer to retry.

Instructions

Step 1: Establish scope

Before any harness_list, harness_get, harness_create, harness_update, or harness_execute call in this skill, establish org/project scope using the repo-wide playbook at references/scope-establishment.md:

  • Parse org / project from the user's message or a pasted Harness UI URL first.
  • Ask only for what is missing — do not re-ask for values already known.
  • Restate the active scope (e.g. org=default, project=payments) before the first mutating call.
  • Never assume a default org/project unless the user explicitly confirms it.

Step 2: Route before acting

Choose the first matching entry route below. Read that entry file first; it may direct you to read additional shared references later.

  • Reference question — the user asks how a fault, probe, action, target workload, tunable, vertex, manifest field, or YAML structure works, without asking to create or modify an experiment: Read references/components.md. No scaffolded YAML is required for a reference-only answer.
  • Existing experiment — the user explicitly asks to edit, update, modify, change, rename, fix, remove from, or add to an existing experiment, says the experiment already exists, or provides an existing experiment UUID: Read references/edit.md. Preserve experimentId and identity. Do not generate a new UUID. Saving an edit reuses harness_create as an upsert — chaos_experiment has no separate update operation; do not call harness_update for this resource type.
  • New experiment — the user asks to create, build, set up, make, design, or launch a new experiment: Read references/create.md. This route still applies when the user supplies the desired name for the new experiment. Generate a new UUID; do not load an existing experiment.
  • Unsure — ask: "Would you like to create a new chaos experiment, edit an existing one, or ask a reference question about experiment YAML/components?"

Read the full file on GitHub · 80 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday Changed · -65 lines · +58 tokens per session ad9f86669304
  2. 11d ago First seen · 145 lines · 62 tokens per session scan A 21a475e0b50b

Subscribe to this mod's changes

chaos-experiment is a skill published in the GitHub repository harness/harness-skills (105 stars, last pushed 2d ago), licensed Apache-2.0. It adds 120 tokens to every session and 1,432 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

foundry-hosted-agent-validation

Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.

microsoft/agent-framework · 82 tokens

build-and-test

How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.

microsoft/agent-framework · 26 tokens

skill-release-gate

Evaluate an Agent Skill bundle for structural integrity, trigger quality, artifact improvement, script correctness, safety, installed-tree integrity, and target-host portability before release.

rohitg00/ai-engineering-from-scratch · 36 tokens

workflow-patterns

Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.

wshobson/agents · 35 tokens

adk-go-self-review

Review an ADK Go change the way a maintainer will — a fresh-context pass over the whole diff, five lenses (correctness and tests, scope, simplicity, style, adk-python parity), and the mutation check that proves your tests pin the change. Use before opening a PR, before any later push that changes code, and when asked…

google/adk-go · 87 tokens

cli-e2e

Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.

ComposioHQ/composio · 62 tokens